Tengyuan Liang

16 catalog papers. Identity-linked publications and additional name matches are distinguished below.

ORCID: 0000-0002-6202-9605

Booth School of Business, The University of Chicago , Chicago, IL 60637 , USA

Publications

• Textual Factors: A Scalable, Interpretable, and Data-Driven Approach to Analyzing Unstructured Information — Management Science 2025
• Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria — Journal of Machine Learning Research 2024 (name-matched, not ORCID-linked)
• Interpolating Classifiers Make Few Mistakes — Journal of Machine Learning Research 2023 (name-matched, not ORCID-linked)
• Universal prediction band via semi-definite programming — Journal of the Royal Statistical Society: Series B (Statistical Methodology) 2022
• Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks — Journal of the American Statistical Association 2022 (name-matched, not ORCID-linked)
• A precise high-dimensional asymptotic theory for boosting and minimum-ℓ1-norm interpolated classifiers — The Annals of Statistics 2022
• Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits — Journal of the American Statistical Association 2021 (name-matched, not ORCID-linked)
• How Well Generative Adversarial Networks Learn Distributions — Journal of Machine Learning Research 2021 (name-matched, not ORCID-linked)
• Deep Neural Networks for Estimation and Inference — Econometrica 2021 (name-matched, not ORCID-linked)
• Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information — Journal of Machine Learning Research 2020 (name-matched, not ORCID-linked)
• Just interpolate: Kernel “Ridgeless” regression can generalize — The Annals of Statistics 2020 (name-matched, not ORCID-linked)
• Statistical inference for the population landscape via moment-adjusted stochastic gradients — Journal of the Royal Statistical Society: Series B (Statistical Methodology) 2019
• Computational and statistical boundaries for submatrix localization in a large noisy matrix — The Annals of Statistics 2017 (name-matched, not ORCID-linked)
• Geometric inference for general high-dimensional linear inverse problems — The Annals of Statistics 2016
• Gaussianized design optimization for covariate balance in randomized experiments — Journal of the Royal Statistical Society: Series B (Statistical Methodology)
• Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction — Journal of the American Statistical Association